sf_trees <- read_csv(here("data", "sf_trees","sf_trees.csv"))
##
## ── Column specification ────────────────────────────────────────────────────────
## cols(
## tree_id = col_double(),
## legal_status = col_character(),
## species = col_character(),
## address = col_character(),
## site_order = col_double(),
## site_info = col_character(),
## caretaker = col_character(),
## date = col_date(format = ""),
## dbh = col_double(),
## plot_size = col_character(),
## latitude = col_double(),
## longitude = col_double()
## )
Refresh some skills for daata wrangling & summary statistics using functions in the ‘dplyr’ paackage.
Find the top 5 highest observations of trees by legal status, do some wrangling, and make a graph.
# Wrangling on types of tree by legal status
top_5_status <- sf_trees %>%
count(legal_status) %>%
drop_na(legal_status) %>% #drop NAs in any row where you don't want them based on column variables
rename(tree_count = n) %>% #new name on the left, old name on the right
relocate(tree_count) %>% #moves tree_count to the first column position
#just keep legal_status categories with top tree_count values
slice_max(tree_count, n = 5) #to identify rows with highest value specified
Make a graph of those top 5 obsesrvations by legal status.
ggplot(data = top_5_status, aes(x = fct_reorder(legal_status, tree_count), y = tree_count)) + #fct_reorder can be reversed (asc vs. desc)
geom_col() +
labs(x = "Legal Status",
y = "Tree Count") +
coord_flip() + #flips the x and y axes
theme_minimal()
Only want to keep observations (rows) for Blackwood Acacia.
blackwood_acacia_Psite <- sf_trees %>%
filter(legal_status == "Permitted Site") #fxn we'll use the most in wrangling data
# Exaample: keep any observations where a certain string is detected anywhere within that variable for an observation
blackwood_acacia <- sf_trees %>%
filter(str_detect(species, "Blackwood Acacia")) %>%
select(legal_status, date, latitude, longitude) #useful for picking/excluding columns, helpful when there are too many
#Plot trees! (A preview! Because R doesn't know these are geographic points yet)
ggplot(data = blackwood_acacia, aes(x = longitude, y = latitude)) +
geom_point()
## Warning: Removed 27 rows containing missing values (geom_point).
Useful for combining or separating fxns.
#split columns by separators
sf_trees_sep <- sf_trees %>%
separate(species, into = c("spp_scientific","spp_common"), sep = "::")
# separate(column, into = c("new column name 1", "new column name 2"), sep = "type of separator")
Example: tidyr::unite()
Combine tree and legal_status columns
sf_trees_unite <- sf_trees %>%
unite("id_status", tree_id:legal_status, sep = "_cool!_")
# unite("name of new united column", column 1 to unite:column 2 to unite, sep = "type of separator")
‘st_as_sf()’ to convert latitude & longitude to spatial coordinates.
# CRS coordinates transforms spherical data for 2d map visualization
blackwood_acacia_sp <- blackwood_acacia %>%
drop_na(longitude, latitude) %>% #get rid of observations where lat or long are missing
st_as_sf(coords = c("longitude", "latitude")) #indicates that variables are storing long and lat data are geographic points. Here in coords = c() you are giving the variable names for the lat and long points
# Assign a data coordinate system of CRS (4326)
st_crs(blackwood_acacia_sp) = 4326
ggplot(data = blackwood_acacia_sp) +
geom_sf(color = "darkgreen")+
theme_void()
Read in SF roads shapefile to give the map meaning!
sf_map <- read_sf(here("data","sf_map", "tl_2017_06075_roads.shp"))
#check using st_transform(sf_map) to make sure it's the correct shp file
#Roads and tree points bust be in the same coordinate system
st_transform(sf_map, 4326)
## Simple feature collection with 4087 features and 4 fields
## geometry type: LINESTRING
## dimension: XY
## bbox: xmin: -122.5136 ymin: 37.70813 xmax: -122.3496 ymax: 37.83213
## geographic CRS: WGS 84
## # A tibble: 4,087 x 5
## LINEARID FULLNAME RTTYP MTFCC geometry
## * <chr> <chr> <chr> <chr> <LINESTRING [°]>
## 1 110498938… Hwy 101 S O… M S1400 (-122.4041 37.74842, -122.404 37.7483, -…
## 2 110498937… Hwy 101 N o… M S1400 (-122.4744 37.80691, -122.4746 37.80684,…
## 3 110366022… Ludlow Aly … M S1780 (-122.4596 37.73853, -122.4596 37.73845,…
## 4 110608181… Mission Bay… M S1400 (-122.3946 37.77082, -122.3929 37.77092,…
## 5 110366689… 25th Ave N M S1400 (-122.4858 37.78953, -122.4855 37.78935,…
## 6 110368970… Willard N M S1400 (-122.457 37.77817, -122.457 37.77812, -…
## 7 110368970… 25th Ave N M S1400 (-122.4858 37.78953, -122.4858 37.78952,…
## 8 110498933… Avenue N M S1400 (-122.3643 37.81947, -122.3638 37.82064,…
## 9 110368970… 25th Ave N M S1400 (-122.4854 37.78983, -122.4858 37.78953)
## 10 110367749… Mission Bay… M S1400 (-122.3865 37.77086, -122.3878 37.77076,…
## # … with 4,077 more rows
#Now plot
ggplot(data = sf_map) +
geom_sf() +
theme_void()
Combine blackwood acacia tree observations & SF roads map:
ggplot()+
geom_sf(data = sf_map, size = 0.1, color = "darkgray")+
geom_sf(data = blackwood_acacia_sp, size = 0.5, color = "red") +
theme_void()
Wouldn’t it be cool if this map was interactive?!
tmap_mode("view") #set tmap mode to interactive viewing
## tmap mode set to interactive viewing
tm_shape(blackwood_acacia_sp) +
tm_dots()
#Now you can zoom in! Turns out there's a blackwood acaia tree on my block!